Model Compression: Make Your Machine Learning Models Lighter and Faster
A deep dive into pruning, quantization, distillation, and other techniques to make your neural networks more efficient and easier to deploy.
Writing
Technical notes, carefully explained.
Notes on machine learning, deep learning, data science, and mathematics.
Articles
Structured Matrices in Deep Learning
How mathematical structure can make neural-network layers smaller and faster, from Toeplitz matrices to Butterfly and Monarch layers.
LLaDA Explained: How Diffusion Could Revolutionize Language Models
Training Large Language Models: From TRPO to GRPO
A Short and Elegant Proof
A concise proof demonstrating that there does not exist a set that contains all sets!
The Number of Wasted Parking Spaces Caused by Random Parking
Estimating the number of wasted parking spaces caused by random parking.
The Math Behind “The Curse of Dimensionality”
The Volume of the n-ball
Derivation of the formula for the volume of the n-ball.